Leadership Instincts: Government launches an Empowered Group chaired by CEO NITI Aayog  |  Teacher Insights: KV Sangathan takes various steps for Online Teaching-Learning Process  |  Education Information: Not Sure of Reliability of News? Get It Verified at Covid19 Fact Check Unit  |  Science Innovations: Covid-19: DST funded startup develops chemical free silver based disinfectant   |  Technology Inceptions: A cost-effective virucidal coating of surgical masks from IIT Kanpur  |  Leadership Instincts: CSIR-IMTECH takes up sample testing for Covid-19  |  Creative Living: Music Industry Turns to Social Media To Bring Solace in Times of Pandemic  |  National Edu News: Hack the Crisis, Online Hackathon for Covid 19 Solutions  |  National Edu News: HRD Minister launches MHRD AICTE COVID-19 Student Helpline Portal   |  Science Innovations: University of Pittsburgh Covid-19 Vaccine Undergoes Animal Trials Successfully  |  Teacher Insights: UNICEF launches #ReadtheWorld initiative for children   |  Science Innovations: Covid-19 -Tracing the Route Map of the Clever Spiky Protein  |  Teacher Insights: Dr Christine Yao announced as BBC New Generation Thinker  |  International Edu News: New research on COVID-19's impact on youth mental health   |  Teacher Insights: Cambridge researchers awarded European Research Council funding  |  
August 21, 2017 Monday 09:36:29 PM IST

Speech recognition by MS a new milestone

Technology Inceptions

San Francisco: Microsofts conversational speech recognition system -- designed to accurately recognises the words in a conversation like humans do -- has reached a 5.1 per cent error rate, its lowest so far.

This milestone means that, for the first time, a computer can recognise the words in a conversation as well as a person would.

"Our research team reached that 5.1 per cent error rate with our speech recognition system, a new industry milestone, substantially surpassing the accuracy we achieved last year," Microsoft said in a blog post late on Sunday.

Last year in October, the team from Microsoft Artificial Intelligence and Research reported a speech recognition system that makes the same or fewer errors than professional transcriptionists. The researchers had then reported a word error rate (WER) of 5.9 percent.


"Last year, Microsoft's speech and dialog research group announced a milestone in reaching human parity on the 'Switchboard' conversational speech recognition task, meaning we had created technology that recognised words in a conversation as well as professional human transcribers," said Xuedong Huang, Technical Fellow, Microsoft.

'Switchboard' is a corpus of recorded telephone conversations that the speech research community has used for more than 20 years to benchmark speech recognition systems. 

The task involves transcribing conversations between strangers discussing topics such as sports and politics. The team used "Microsoft Cognitive Toolkit 2.1" (CNTK), the most scalable deep learning software available, for exploring model architectures. 

Additionally, Microsoft's investment in cloud compute infrastructure, specifically Azure GPUs, helped improve the effectiveness and speed.


Reaching human parity with an accuracy on par with humans has been a research goal for the last 25 years. 

"Microsoft's willingness to invest in long-term research is now paying dividends for our customers in products and services such as Cortana, Presentation Translator, and Microsoft Cognitive Services," the post read. "Moving from recognising to understanding speech is the next major frontier for speech technology," the post added.

Comments